Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    math formulas and code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     عراق
    -0.07
    legant
    -0.06
     /**
    -0.06
    (F
    -0.06
    -terrorism
    -0.06
     Soup
    -0.06
    myfile
    -0.06
     dear
    -0.06
     conexión
    -0.06
    ोत
    -0.06
    POSITIVE LOGITS
    지요
    0.06
    -operator
    0.06
     çalışmalar
    0.06
     永
    0.06
     trong
    0.06
     đề
    0.06
     बन
    0.06
     용
    0.06
     knock
    0.06
     حتى
    0.06
    Act Density 0.063%

    No Known Activations